This article describes the use of artificial intelligence technology, artificial neural networks (ANNs), in analysing multivariate data relating to the functional well-being of older people.
ANNs are a relatively new set of data mining techniques that have been developed to extract information from complex databases and datasets that cannot be readily detected by conventional statistical analysis.
This article describes one such technique, the Kohonen Self-Organizing Map (KSOM), and how it has been used to analyse EASY (Elderly Assessment System) data collected in Belfast and Southampton.
EASY is a multidimensional health outcome assessment system, which has been developed to assess the health and social functioning of older people as part of routine care in community settings.
A database has been established at the University of Sheffield (in collaboration with the World Health Organization Regional Office for Europe) to analyse and compare EASY data collected from different centres throughout Europe.
This article reports the use of the KSOM technique in the secondary analysis of EASY data relating to the instrumental activities of daily living (IADL) of older people in community settings in Belfast and Southampton.
The analysis revealed a hierarchical classificatior of dependence in IADL amongst older people and demonstrates the use of ANNs as a data analysis tool complementary to more traditional techniques.
Mots-clés Pascal : Classification, Capacité fonctionnelle, Dépendance, Vieillard, Homme, Intelligence artificielle, Réseau neuronal, Technique, Méthodologie, Activité, Vie quotidienne, Evaluation
Mots-clés Pascal anglais : Classification, Functional capacity, Dependence, Elderly, Human, Artificial intelligence, Neural network, Technique, Methodology, Activity, Daily living, Evaluation
Notice produite par :
Inist-CNRS - Institut de l'Information Scientifique et Technique
Cote : 98-0079195
Code Inist : 002B30A11. Création : 14/05/1998.